• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 98 subscribers
  • Views 317 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA2EVM5777: Caffe Jacinto Input data channel

WEI CHIH CHERN
Intellectual 320 points

Part Number: TDA2EVM5777

Hello,

The provided script has no toggle for using signle-channel images (grayscale) as input.  What needs to be changed for training a SSD model that take a single channel images as input?

Thanks,

Wei Chih

  • 0
    TI__Genius 11506 points

    Wei Chih,

    Frankly, I have not trained using gray scale images in Caffe - so i don't know.

    A workaround is - convert your images into 3 channels and save them - I think you can use Python packages such as opencv or PIL to do that. 

    Best regards,

    Manu.